Guardado en:
Detalles Bibliográficos
Autores principales: Limkonchotiwat, Peerat, Masuk, Kanruethai, Nonesung, Surapon, Mai-On, Chalermpun, Nutanong, Sarana, Ponwitayarat, Wuttikorn, Manakul, Potsawee
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2504.05898
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908306945081344
author Limkonchotiwat, Peerat
Masuk, Kanruethai
Nonesung, Surapon
Mai-On, Chalermpun
Nutanong, Sarana
Ponwitayarat, Wuttikorn
Manakul, Potsawee
author_facet Limkonchotiwat, Peerat
Masuk, Kanruethai
Nonesung, Surapon
Mai-On, Chalermpun
Nutanong, Sarana
Ponwitayarat, Wuttikorn
Manakul, Potsawee
contents Large language models show promising results in various NLP tasks. Despite these successes, the robustness and consistency of LLMs in underrepresented languages remain largely unexplored, especially concerning local dialects. Existing benchmarks also focus on main dialects, neglecting LLMs' ability on local dialect texts. In this paper, we introduce a Thai local dialect benchmark covering Northern (Lanna), Northeastern (Isan), and Southern (Dambro) Thai, evaluating LLMs on five NLP tasks: summarization, question answering, translation, conversation, and food-related tasks. Furthermore, we propose a human evaluation guideline and metric for Thai local dialects to assess generation fluency and dialect-specific accuracy. Results show that LLM performance declines significantly in local Thai dialects compared to standard Thai, with only proprietary models like GPT-4o and Gemini2 demonstrating some fluency
format Preprint
id arxiv_https___arxiv_org_abs_2504_05898
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Assessing Thai Dialect Performance in LLMs with Automatic Benchmarks and Human Evaluation
Limkonchotiwat, Peerat
Masuk, Kanruethai
Nonesung, Surapon
Mai-On, Chalermpun
Nutanong, Sarana
Ponwitayarat, Wuttikorn
Manakul, Potsawee
Computation and Language
Large language models show promising results in various NLP tasks. Despite these successes, the robustness and consistency of LLMs in underrepresented languages remain largely unexplored, especially concerning local dialects. Existing benchmarks also focus on main dialects, neglecting LLMs' ability on local dialect texts. In this paper, we introduce a Thai local dialect benchmark covering Northern (Lanna), Northeastern (Isan), and Southern (Dambro) Thai, evaluating LLMs on five NLP tasks: summarization, question answering, translation, conversation, and food-related tasks. Furthermore, we propose a human evaluation guideline and metric for Thai local dialects to assess generation fluency and dialect-specific accuracy. Results show that LLM performance declines significantly in local Thai dialects compared to standard Thai, with only proprietary models like GPT-4o and Gemini2 demonstrating some fluency
title Assessing Thai Dialect Performance in LLMs with Automatic Benchmarks and Human Evaluation
topic Computation and Language
url https://arxiv.org/abs/2504.05898